Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -525.73 +/- 202.46
+      value: 252.87 +/- 17.16
       name: mean_reward
       verified: false
 ---

config.json

@@ -1 +1 @@
-{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7fa0f6cea0e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa0f6cea170>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa0f6cea200>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa0f6cea290>", "_build": "<function ActorCriticPolicy._build at 0x7fa0f6cea320>", "forward": "<function ActorCriticPolicy.forward at 0x7fa0f6cea3b0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fa0f6cea440>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa0f6cea4d0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fa0f6cea560>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa0f6cea5f0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa0f6cea680>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa0f6cea710>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fa0f74f6640>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 0.0, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": null, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 1.0, "_stats_window_size": 100, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7906091a1d80>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7906091a1e10>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7906091a1ea0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7906091a1f30>", "_build": "<function ActorCriticPolicy._build at 0x7906091a1fc0>", "forward": "<function ActorCriticPolicy.forward at 0x7906091a2050>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7906091a20e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7906091a2170>", "_predict": "<function ActorCriticPolicy._predict at 0x7906091a2200>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7906091a2290>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7906091a2320>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7906091a23b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7906091a5740>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1689421463215853616, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.109+-x86_64-with-glibc2.31 # 1 SMP Fri Jun 9 10:57:30 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b622764b6f713ac18090402d7d31c53795839ba6b110e42104483ed1fa7ae66
+size 146754

ppo-LunarLander-v2/_stable_baselines3_version

@@ -0,0 +1 @@
+2.0.0a5

ppo-LunarLander-v2/data

@@ -0,0 +1,99 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
+        "__module__": "stable_baselines3.common.policies",
+        "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7906091a1d80>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7906091a1e10>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7906091a1ea0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7906091a1f30>",
+        "_build": "<function ActorCriticPolicy._build at 0x7906091a1fc0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7906091a2050>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7906091a20e0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7906091a2170>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7906091a2200>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7906091a2290>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7906091a2320>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7906091a23b0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7906091a5740>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1689421463215853616,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.015808000000000044,
+    "_stats_window_size": 100,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 248,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True  True  True]",
+        "_shape": [
+            8
+        ],
+        "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]",
+        "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]",
+        "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]",
+        "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
+        "n": "4",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "n_steps": 1024,
+    "gamma": 0.999,
+    "gae_lambda": 0.98,
+    "ent_coef": 0.01,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 64,
+    "n_epochs": 4,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    }
+}

ppo-LunarLander-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8ad147f1913da8545e14b81de4a59c8e0ed2a1a1d5bbbfc30644fac22dd1644
+size 87929

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e582910cb7dad1890b7f38518a85b8ac7c464d0a9c2ab5e9acfc2abb4ab84ad2
+size 43329

ppo-LunarLander-v2/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
+size 431

ppo-LunarLander-v2/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.15.109+-x86_64-with-glibc2.31 # 1 SMP Fri Jun 9 10:57:30 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.0.1+cu118
+- GPU Enabled: True
+- Numpy: 1.22.4
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

results.json

@@ -1 +1 @@
-{"mean_reward": -525.7271877999999, "std_reward": 202.4596675960015, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-01T17:41:13.652212"}
+{"mean_reward": 252.8701145196669, "std_reward": 17.155748672409825, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-15T12:18:30.938614"}